Web & Data

Deterministic decision procedure for choosing the correct web access method in the new MCP-everywhere landscape. Given a retrieval task, evaluate WebMCP inherited interfaces, Kitesurf worker-side browser, headless browser, scrape API, paid data API, and plain HTTP GET against latency, cost, data freshness, anti-bot complexity, and schema-stability thresholds. Output a method verdict with numeric triggers, fallback order, and kill criteria.

Cross-verified: Top Hacker News stories for a topic, ranked by points and comments. Combined with recent arxiv papers for a topic with titles and dates.

Cross-verified: GitHub repo metadata: license, stars, maintenance state. Combined with osv vulnerability scan for a package with a pinned-or-upgrade verdict.

Cross-verified: Geocode a place: weather, local time, UTC offset. Combined with base address balance/activity/contract check.

List Polymarket events with cursor-based keyset pagination

Get a person's email addresses.

Resolve a legal entity against the public GLEIF registry by LEI, legal name, jurisdiction, registration ID or country, with ranked matches and auditable registry evidence

Validate an IBAN and retrieve associated bank details, country, and check digits.

Polymarket event search.

Recommends a Base (EVM) transaction priority fee (maxPriorityFeePerGas, in gwei) based on recent network activity

Get paginated list of supported job title values with optional search.

Fetch and extract the readable content of a single URL. Returns the page title, publish date when known, the most relevant excerpts (optionally focused by an `objective`), and the full readable text of the page.

Passive subdomain enumeration for a domain via public sources (subfinder).

Describe an ideal customer profile in plain text. Returns a job_id immediately; results are delivered asynchronously via the optional webhook_url or by polling the job status endpoint. Flat rate per run.

Retrieves profile information for political figures or entities.

Structured parse of a public web page: main text, headings, links, tables and rich metadata (description, canonical, lang, Open Graph, Twitter cards, JSON-LD) as separate fields. Browserless, robots.txt-respecting.

Returns data on lobbying expenditures and spending activities.

Returns crime incident data and records.

Fetch a public URL and return clean markdown/text + metadata (trafilatura).

Free-text web search returning a ranked list of title/url/snippet results. The default backend is a multi-engine auto-fusion across Brave, DuckDuckGo, Google, Wikipedia, Yandex and more (deduped by URL + ranked) — not a single engine. Optio

Retrieves or grants access to information about upcoming events or features.

Retrieves academic scholar or author information and publication data.

Retrieves news articles and events from the GDELT global event database.

GitHub repository health & intelligence for due-diligence / dependency choice: stars, forks, open issues, watchers, size, language, topics, license, archived/fork flags, and computed signals (days_since_push, age, issues_per_star, is_active). From the official GitHub REST API, normalized.